xlm-roberta-base-sadilar-ner is the first
Named Entity Recognition model for 10 South African languages (Afrikaans, isiNdebele, isiXhosa, isiZulu, Sepedi, Sesotho, Setswana, siSwati, Tshivenda and Xitsonga) based on a fine-tuned XLM-RoBERTa large model. It achieves the
state-of-the-art performance for the NER task. It has been trained to recognize three types of entities: location (LOC), organizations (ORG), and person (PER).
Specifically, this model is a
xlm-roberta-large model that was fine-tuned on an aggregation of South African languages datasets obtained from
SADILAR dataset.
1from transformers import AutoTokenizer, AutoModelForTokenClassification
2from transformers import pipeline
3tokenizer = AutoTokenizer.from_pretrained("Davlan/xlm-roberta-base-sadilar-ner")
4model = AutoModelForTokenClassification.from_pretrained("Davlan/xlm-roberta-base-sadilar-ner")
5nlp = pipeline("ner", model=model, tokenizer=tokenizer)
6example = "Kuchaza kona ukuthi uMengameli uMnuz Cyril Ramaphosa, usebatshelile ukuthi uzosikhipha maduze isitifiketi."
7ner_results = nlp(example)
8print(ner_results)
This model is limited by its training dataset of entity-annotated news articles from a specific span of time. This may not generalize well for all use cases in different domains.
This model was fine-tuned on 10 African NER datasets (Afrikaans, isiNdebele, isiXhosa, isiZulu, Sepedi, Sesotho, Setswana, siSwati, Tshivenda and Xitsonga)
SADILAR dataset
The training dataset distinguishes between the beginning and continuation of an entity so that if there are back-to-back entities of the same type, the model can output where the second entity begins. As in the dataset, each token will be classified as one of the following classes:
